中文
相关论文

相关论文: Private Approximations of the 2nd-Moment Matrix Us…

200 篇论文

Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision…

机器学习 · 计算机科学 2022-03-22 Xingyu Zhou

We present the first differentially private algorithms for reinforcement learning, which apply to the task of evaluating a fixed policy. We establish two approaches for achieving differential privacy, provide a theoretical analysis of the…

机器学习 · 计算机科学 2016-03-08 Borja Balle , Maziar Gomrokchi , Doina Precup

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…

机器学习 · 计算机科学 2021-09-07 Ashly Lau , Jonathan Passerat-Palmbach

Differential privacy is a cryptographically-motivated definition of privacy which has gained significant attention over the past few years. Differentially private solutions enforce privacy by adding random noise to a function computed over…

机器学习 · 计算机科学 2012-07-03 Kamalika Chaudhuri , Daniel Hsu

It is difficult to continually update private machine learning models with new data while maintaining privacy. Data incur increasing privacy loss -- as measured by differential privacy -- when they are used in repeated computations. In this…

机器学习 · 计算机科学 2022-03-08 Lauren Watson , Abhirup Ghosh , Benedek Rozemberczki , Rik Sarkar

With the wide application of machine learning techniques in practice, privacy preservation has gained increasing attention. Protecting user privacy with minimal accuracy loss is a fundamental task in the data analysis and mining community.…

机器学习 · 统计学 2026-02-02 Haixia Liu , Ruifan Huang

We study the canonical statistical estimation problem of linear regression from $n$ i.i.d.~examples under $(\varepsilon,\delta)$-differential privacy when some response variables are adversarially corrupted. We propose a variant of the…

机器学习 · 计算机科学 2023-02-01 Xiyang Liu , Prateek Jain , Weihao Kong , Sewoong Oh , Arun Sai Suggala

Differential privacy is a restriction on data processing algorithms that provides strong confidentiality guarantees for individual records in the data. However, research on proper statistical inference, that is, research on properly…

密码学与安全 · 计算机科学 2021-07-06 Joerg Drechsler , Ira Globus-Harris , Audra McMillan , Jayshree Sarathy , Adam Smith

In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training. (Here, public data refers to auxiliary data sets that have no privacy…

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

机器学习 · 统计学 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

Machine learning models are increasingly utilized across impactful domains to predict individual outcomes. As such, many models provide algorithmic recourse to individuals who receive negative outcomes. However, recourse can be leveraged by…

机器学习 · 计算机科学 2023-08-09 Catherine Huang , Chelse Swoopes , Christina Xiao , Jiaqi Ma , Himabindu Lakkaraju

Nowadays, owners and developers of deep learning models must consider stringent privacy-preservation rules of their training data, usually crowd-sourced and retaining sensitive information. The most widely adopted method to enforce privacy…

机器学习 · 计算机科学 2022-09-08 Eugenio Lomurno , Matteo matteucci

Differential privacy has gained popularity in machine learning as a strong privacy guarantee, in contrast to privacy mitigation techniques such as k-anonymity. However, applying differential privacy to n-gram counts significantly degrades…

密码学与安全 · 计算机科学 2021-02-01 Osman Ramadan , James Withers , Douglas Orr

Local differential privacy is a differential privacy paradigm in which individuals first apply a privacy mechanism to their data (often by adding noise) before transmitting the result to a curator. The noise for privacy results in…

统计方法学 · 统计学 2023-10-17 Yuki Ohnishi , Jordan Awan

Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privacy guarantee, many learning systems now incorporate…

机器学习 · 计算机科学 2021-03-19 Xiangyi Chen , Zhiwei Steven Wu , Mingyi Hong

Differentially private distributed stochastic optimization has become a hot topic due to the urgent need of privacy protection in distributed stochastic optimization. In this paper, two-time scale stochastic approximation-type algorithms…

系统与控制 · 电气工程与系统科学 2024-03-19 Jimin Wang , Ji-Feng Zhang

We study the conjugacy approximation method in the context of Bayesian ranking and selection with unknown correlations. Under the assumption of normal-inverse-Wishart prior distribution, the posterior distribution remains a…

统计计算 · 统计学 2017-11-16 Qiong Zhang , Yongjia Song

In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD…

机器学习 · 计算机科学 2024-01-02 Rachel Redberg , Antti Koskela , Yu-Xiang Wang

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…

We show that Thompson Sampling with Gaussian Prior as detailed by Algorithm 2 in (Agrawal & Goyal, 2013) is already differentially private. Theorem 1 show that it enjoys a very competitive privacy loss of only $\mathcal{O}(\ln^2 T)$ after T…

密码学与安全 · 计算机科学 2018-06-26 Aristide C. Y. Tossou , Christos Dimitrakakis